Triple
T11525181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Tyndall |
E273274
|
entity |
| Predicate | isClimbedBy |
P40582
|
FINISHED |
| Object | experienced hikers |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: experienced hikers | Statement: [Mount Tyndall, isClimbedBy, experienced hikers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isClimbedBy Context triple: [Mount Tyndall, isClimbedBy, experienced hikers]
-
A.
climbedBy
chosen
Indicates that something is ascended or scaled by an agent or entity.
-
B.
isClimbedIn
Indicates that an entity (typically a person or animal) ascends or climbs while being located within or inside another entity (such as a structure, vehicle, or environment).
-
C.
canBeClimbedIn
Indicates that one entity is suitable or possible to climb while being inside or within another entity.
-
D.
hasClimbFrom
Indicates a relationship where one location or object serves as the starting point from which a climb or ascent to another location or object begins.
-
E.
climbedWith
Indicates that one entity climbed together with another entity, sharing the ascent as a joint activity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d87fd379648190b342e0c4b4f685b7 |
completed | April 10, 2026, 4:42 a.m. |
| PD | Predicate disambiguation | batch_69d80879fdb48190be6dacc8aa63c809 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.